I am a research scientist at Meta Reality Labs. I received my Doctorate from University of California, San Diego, advised by Prof. Manmohan Chandraker.  Before that, I received my Bachelor's degree from Tsinghua University, advised by Prof. Jiansheng Chen. Throughout my studies, I was also fortunate to be mentored by Prof. Ravi Ramamoorthi, Kalyan Sunkavalli, Miloš Hašan, Zhao Dong, and Prof. Olga Veksler.

My research interest is in inverse rendering, scene understanding, neural rendering and 3D foundation models. I am honored to receive Powell Fellowship (2016), Qualcomm Innovation Fellowship (2020), and UCSD CSE Best Doctoral Dissertation Award (2022). 

Internships at Meta: Please feel free to send me your CV and research interest to my personal email (lizhengqin2012-at-gmail-dot-com) or company email (zhl-at-meta-dot-com).

Selected Publications

TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion, CVPR 2024

Spatiotemporally Consistent HDR Indoor Lighting Estimation, ACM Transaction on Graphics (Present in SIGGRAPH Asia 2023)

Efficient Graphics Representation with Differentiable Indirection, SIGGRAPH Asia 2023 (Conference track)

Neural-PBIR Reconstruction of Shape, Material, and Illumination, ICCV 2023 (Best relighting results on the Stanford-ORB dataset)  

Physically-based editing of indoor scene lighting from a single image, ECCV 2022 (Oral presentation)  

IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes, CVPR 2022 (Oral presentation)

PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes, CVPR 2022

OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets, CVPR 2021 (Oral presentation)

Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image, CVPR 2020 (Oral presentation)

Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes, CVPR 2020 (Oral presentation)

Zhengqin Li*, Yu-Ying Yeh*, Manmohan Chandraker (*Equal contribution)

[project page][paper][dataset][code]

Learning to Reconstruct Shape and Spatially-Varying Reflectance with a Single Image, SIGGRAPH Asia 2018

Learning to See through Turbulent Water, WACV 2018

Robust Energy Minimization for BRDF-Invariant Shape from Light Fields, CVPR 2017

Superpixel Segmentation Using Linear Spectral Clustering, CVPR 2015 (Algorithm included in OpenCV)

Zhengqin Li, Jiansheng Chen

[paper][code]

Doctoral Dissertation

Physically-Motivated Learning For Photorealistic Scene Reconstruction and Editing in the Wild (UCSD CSE Best Dcotoral Dissertation Award)

Others

Weakly Supervised Semantic Segmentation Using Graph-cut (Tsinghua EE Outstanding Bachelor's Thesis Award)

A Report on Double Expansion: Definition, Algorithm and Properties (Part of theoretical results included in BMVC 2017)

Zhengqin Li, Olga Veksler

[paper]

Previous interns: Cheng Sun (Now at Nvidia Research), Yu-Ying Yeh

Honors and Awards


2022 Best Doctoral Dissertation Award, UC San Diego

2021 CVPR, ICCV Outstanding Reviewer Awards, UC San Diego

2020 Qualcomm Innovation Fellowship, UC San Diego

2019, 2020 Adobe Fellowship finalist, UC San Diego

2016 Powell Fellowship, UC San Diego

2016 Outstanding Bachelor's Thesis, Tsinghua University

2012-2016 Academic Excellence Awards, Tsinghua University